A new stroke prediction model combined algorithm based on artificial neural networks and logistic regression

Jiehao Fu

doi:10.1117/12.2656802

20 October 2022 A new stroke prediction model combined algorithm based on artificial neural networks and logistic regression

Jiehao Fu

Author Affiliations +

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 1245147 (2022) https://doi.org/10.1117/12.2656802
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

Stroke is an important factor contributed to cause of death worldwide. It is particularly important to build a model to accurately predict the incidence of stroke. Traditional models typically select only one common binary classification algorithm for prediction. This paper proposes a method that uses artificial neural networks (ANNs) algorithm to complete feature extraction and learning of the data, and then selects a suitable binary classification algorithm and combines them to build the model. Data preprocessing as well as data visualization analysis was first performed on a stroke dataset using Python. The models were then trained separately using different algorithms, among which logistic regression performed the best. Finally, a combined algorithm using it and artificial neural networks was used to construct the prediction model. The AUC values were employed in this case to evaluate the performance of the model and the experimental results indicated that the AUC values of the new model were approximately 0.39% higher than those of the logistic regression-only model. This indicates that the new model outperforms the traditional prediction model to some extent.

Citation Download Citation

Jiehao Fu "A new stroke prediction model combined algorithm based on artificial neural networks and logistic regression", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 1245147 (20 October 2022); https://doi.org/10.1117/12.2656802

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available